From cb7e0e130503cb8e5ee6a7e8983bf71ed408516f Mon Sep 17 00:00:00 2001
From: Parav Pandit <parav@mellanox.com>
Date: Tue, 26 Feb 2019 14:01:48 +0200
Subject: RDMA/core: Add interface to read device namespace sharing mode

Add an interface via netlink command to query whether rdma devices are
shared among multiple net namespaces or not. When using RDMAtool, it can
be queried as,

$rdma system show netns
netns shared

Signed-off-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
---
 include/uapi/rdma/rdma_netlink.h | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

(limited to 'include/uapi')

diff --git a/include/uapi/rdma/rdma_netlink.h b/include/uapi/rdma/rdma_netlink.h
index 5cc592728071..6af88c736073 100644
--- a/include/uapi/rdma/rdma_netlink.h
+++ b/include/uapi/rdma/rdma_netlink.h
@@ -261,7 +261,8 @@ enum rdma_nldev_command {
 
 	RDMA_NLDEV_CMD_PORT_GET, /* can dump */
 
-	/* 6 - 8 are free to use */
+	RDMA_NLDEV_CMD_SYS_GET, /* can dump */
+	/* 7 - 8 are free to use */
 
 	RDMA_NLDEV_CMD_RES_GET = 9, /* can dump */
 
@@ -472,6 +473,12 @@ enum rdma_nldev_attr {
 	 */
 	RDMA_NLDEV_ATTR_LINK_TYPE,		/* string */
 
+	/*
+	 * net namespace mode for rdma subsystem:
+	 * either shared or exclusive among multiple net namespaces.
+	 */
+	RDMA_NLDEV_SYS_ATTR_NETNS_MODE,		/* u8 */
+
 	/*
 	 * Always the end
 	 */
-- 
cgit v1.2.3-59-g8ed1b


From 2b34c558022673c0d6393dd7941d417f1b5a7236 Mon Sep 17 00:00:00 2001
From: Parav Pandit <parav@mellanox.com>
Date: Tue, 26 Feb 2019 14:01:49 +0200
Subject: RDMA/core: Add command to set ib_core device net namspace sharing
 mode

Add netlink command that enables/disables sharing rdma device among
multiple net namespaces.

Using rdma tool,
$rdma sys set netns shared (default mode)

When rdma subsystem netns mode is set to shared mode, rdma devices
will be accessible in all net namespaces.

Using rdma tool,
$rdma sys set netns exclusive

When rdma subsystem netns mode is set to exclusive mode, devices
will be accessible in only one net namespace at any given
point of time.

If there are any net namespaces other than default init_net exists,
while executing this command, it will fail and mode cannot be changed.

To change this mode, netlink command is used instead of sysctl, because
netlink command allows to auto load a module.

Signed-off-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
---
 drivers/infiniband/core/core_priv.h |  2 +
 drivers/infiniband/core/device.c    | 87 +++++++++++++++++++++++++++++++++++++
 drivers/infiniband/core/nldev.c     | 25 +++++++++++
 include/uapi/rdma/rdma_netlink.h    |  4 +-
 4 files changed, 117 insertions(+), 1 deletion(-)

(limited to 'include/uapi')

diff --git a/drivers/infiniband/core/core_priv.h b/drivers/infiniband/core/core_priv.h
index 30c7d4a46b76..0663fc64e950 100644
--- a/drivers/infiniband/core/core_priv.h
+++ b/drivers/infiniband/core/core_priv.h
@@ -342,4 +342,6 @@ struct net_device *rdma_read_gid_attr_ndev_rcu(const struct ib_gid_attr *attr);
 void ib_free_port_attrs(struct ib_core_device *coredev);
 int ib_setup_port_attrs(struct ib_core_device *coredev,
 			bool alloc_hw_stats);
+
+int rdma_compatdev_set(u8 enable);
 #endif /* _CORE_PRIV_H */
diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index 0605208a73d3..2dbd04739ac6 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -766,6 +766,7 @@ static int add_one_compat_dev(struct ib_device *device,
 	struct ib_core_device *cdev;
 	int ret;
 
+	lockdep_assert_held(&rdma_nets_rwsem);
 	if (!ib_devices_shared_netns)
 		return 0;
 
@@ -870,6 +871,87 @@ static int add_compat_devs(struct ib_device *device)
 	return ret;
 }
 
+static void remove_all_compat_devs(void)
+{
+	struct ib_compat_device *cdev;
+	struct ib_device *dev;
+	unsigned long index;
+
+	down_read(&devices_rwsem);
+	xa_for_each (&devices, index, dev) {
+		unsigned long c_index = 0;
+
+		/* Hold nets_rwsem so that any other thread modifying this
+		 * system param can sync with this thread.
+		 */
+		down_read(&rdma_nets_rwsem);
+		xa_for_each (&dev->compat_devs, c_index, cdev)
+			remove_one_compat_dev(dev, c_index);
+		up_read(&rdma_nets_rwsem);
+	}
+	up_read(&devices_rwsem);
+}
+
+static int add_all_compat_devs(void)
+{
+	struct rdma_dev_net *rnet;
+	struct ib_device *dev;
+	unsigned long index;
+	int ret = 0;
+
+	down_read(&devices_rwsem);
+	xa_for_each_marked (&devices, index, dev, DEVICE_REGISTERED) {
+		unsigned long net_index = 0;
+
+		/* Hold nets_rwsem so that any other thread modifying this
+		 * system param can sync with this thread.
+		 */
+		down_read(&rdma_nets_rwsem);
+		xa_for_each (&rdma_nets, net_index, rnet) {
+			ret = add_one_compat_dev(dev, rnet);
+			if (ret)
+				break;
+		}
+		up_read(&rdma_nets_rwsem);
+	}
+	up_read(&devices_rwsem);
+	if (ret)
+		remove_all_compat_devs();
+	return ret;
+}
+
+int rdma_compatdev_set(u8 enable)
+{
+	struct rdma_dev_net *rnet;
+	unsigned long index;
+	int ret = 0;
+
+	down_write(&rdma_nets_rwsem);
+	if (ib_devices_shared_netns == enable) {
+		up_write(&rdma_nets_rwsem);
+		return 0;
+	}
+
+	/* enable/disable of compat devices is not supported
+	 * when more than default init_net exists.
+	 */
+	xa_for_each (&rdma_nets, index, rnet) {
+		ret++;
+		break;
+	}
+	if (!ret)
+		ib_devices_shared_netns = enable;
+	up_write(&rdma_nets_rwsem);
+	if (ret)
+		return -EBUSY;
+
+	if (enable)
+		ret = add_all_compat_devs();
+	else
+		remove_all_compat_devs();
+	return ret;
+}
+
 static void rdma_dev_exit_net(struct net *net)
 {
 	struct rdma_dev_net *rnet = net_generic(net, rdma_dev_net_id);
@@ -923,7 +1005,12 @@ static __net_init int rdma_dev_init_net(struct net *net)
 
 	down_read(&devices_rwsem);
 	xa_for_each_marked (&devices, index, dev, DEVICE_REGISTERED) {
+		/* Hold nets_rwsem so that netlink command cannot change
+		 * system configuration for device sharing mode.
+		 */
+		down_read(&rdma_nets_rwsem);
 		ret = add_one_compat_dev(dev, rnet);
+		up_read(&rdma_nets_rwsem);
 		if (ret)
 			break;
 	}
diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c
index 49c048738f94..28b4ed8f9930 100644
--- a/drivers/infiniband/core/nldev.c
+++ b/drivers/infiniband/core/nldev.c
@@ -1341,6 +1341,27 @@ static int nldev_get_sys_get_dumpit(struct sk_buff *skb,
 	return skb->len;
 }
 
+static int nldev_set_sys_set_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
+				  struct netlink_ext_ack *extack)
+{
+	struct nlattr *tb[RDMA_NLDEV_ATTR_MAX];
+	u8 enable;
+	int err;
+
+	err = nlmsg_parse(nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1,
+			  nldev_policy, extack);
+	if (err || !tb[RDMA_NLDEV_SYS_ATTR_NETNS_MODE])
+		return -EINVAL;
+
+	enable = nla_get_u8(tb[RDMA_NLDEV_SYS_ATTR_NETNS_MODE]);
+	/* Only 0 and 1 are supported */
+	if (enable > 1)
+		return -EINVAL;
+
+	err = rdma_compatdev_set(enable);
+	return err;
+}
+
 static const struct rdma_nl_cbs nldev_cb_table[RDMA_NLDEV_NUM_OPS] = {
 	[RDMA_NLDEV_CMD_GET] = {
 		.doit = nldev_get_doit,
@@ -1389,6 +1410,10 @@ static const struct rdma_nl_cbs nldev_cb_table[RDMA_NLDEV_NUM_OPS] = {
 	[RDMA_NLDEV_CMD_SYS_GET] = {
 		.dump = nldev_get_sys_get_dumpit,
 	},
+	[RDMA_NLDEV_CMD_SYS_SET] = {
+		.doit = nldev_set_sys_set_doit,
+		.flags = RDMA_NL_ADMIN_PERM,
+	},
 };
 
 void __init nldev_init(void)
diff --git a/include/uapi/rdma/rdma_netlink.h b/include/uapi/rdma/rdma_netlink.h
index 6af88c736073..9bba001a7347 100644
--- a/include/uapi/rdma/rdma_netlink.h
+++ b/include/uapi/rdma/rdma_netlink.h
@@ -262,7 +262,9 @@ enum rdma_nldev_command {
 	RDMA_NLDEV_CMD_PORT_GET, /* can dump */
 
 	RDMA_NLDEV_CMD_SYS_GET, /* can dump */
-	/* 7 - 8 are free to use */
+	RDMA_NLDEV_CMD_SYS_SET,
+
+	/* 8 is free to use */
 
 	RDMA_NLDEV_CMD_RES_GET = 9, /* can dump */
 
-- 
cgit v1.2.3-59-g8ed1b


From 065d55237ad1c72bb849434542842e1328305a29 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Sun, 10 Mar 2019 17:27:45 +0200
Subject: RDMA/netlink: Remove unused data structure

Delete structure which is not connected due to removal in commit
cited in Fixes line.

Fixes: a78e8723a505 ("RDMA/cma: Remove CM_ID statistics provided by rdma-cm module")
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
---
 include/uapi/rdma/rdma_netlink.h | 11 -----------
 1 file changed, 11 deletions(-)

(limited to 'include/uapi')

diff --git a/include/uapi/rdma/rdma_netlink.h b/include/uapi/rdma/rdma_netlink.h
index 9bba001a7347..3a231a989974 100644
--- a/include/uapi/rdma/rdma_netlink.h
+++ b/include/uapi/rdma/rdma_netlink.h
@@ -49,17 +49,6 @@ enum {
 	RDMA_NL_IWPM_NUM_OPS
 };
 
-struct rdma_cm_id_stats {
-	__u32	qp_num;
-	__u32	bound_dev_if;
-	__u32	port_space;
-	__s32	pid;
-	__u8	cm_state;
-	__u8	node_type;
-	__u8	port_num;
-	__u8	qp_type;
-};
-
 enum {
 	IWPM_NLA_REG_PID_UNSPEC = 0,
 	IWPM_NLA_REG_PID_SEQ,
-- 
cgit v1.2.3-59-g8ed1b


From 9e886b39a73ad0219b3f2ff574c135d770118a6b Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Tue, 2 Apr 2019 21:50:34 +0300
Subject: RDMA/nldev: Return device protocol

Add new RDMA_NLDEV_ATTR_DEV_PROTOCOL attribute to give ability for UDEV
rules create IB device stable names based on link type protocol.  The
assumption that devices like mlx4 with duality in their link type under
one IB device struct won't be allowed in the future.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
---
 drivers/infiniband/core/nldev.c  | 24 +++++++++++++++++++++++-
 include/uapi/rdma/rdma_netlink.h |  5 +++++
 2 files changed, 28 insertions(+), 1 deletion(-)

(limited to 'include/uapi')

diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c
index 28b4ed8f9930..8cb3851d212e 100644
--- a/drivers/infiniband/core/nldev.c
+++ b/drivers/infiniband/core/nldev.c
@@ -117,6 +117,8 @@ static const struct nla_policy nldev_policy[RDMA_NLDEV_ATTR_MAX] = {
 	[RDMA_NLDEV_ATTR_LINK_TYPE]		= { .type = NLA_NUL_STRING,
 				    .len = RDMA_NLDEV_ATTR_ENTRY_STRLEN },
 	[RDMA_NLDEV_SYS_ATTR_NETNS_MODE]	= { .type = NLA_U8 },
+	[RDMA_NLDEV_ATTR_DEV_PROTOCOL]		= { .type = NLA_NUL_STRING,
+				    .len = RDMA_NLDEV_ATTR_ENTRY_STRLEN },
 };
 
 static int put_driver_name_print_type(struct sk_buff *msg, const char *name,
@@ -199,6 +201,8 @@ static int fill_nldev_handle(struct sk_buff *msg, struct ib_device *device)
 static int fill_dev_info(struct sk_buff *msg, struct ib_device *device)
 {
 	char fw[IB_FW_VERSION_NAME_MAX];
+	int ret = 0;
+	u8 port;
 
 	if (fill_nldev_handle(msg, device))
 		return -EMSGSIZE;
@@ -227,7 +231,25 @@ static int fill_dev_info(struct sk_buff *msg, struct ib_device *device)
 		return -EMSGSIZE;
 	if (nla_put_u8(msg, RDMA_NLDEV_ATTR_DEV_NODE_TYPE, device->node_type))
 		return -EMSGSIZE;
-	return 0;
+
+	/*
+	 * Link type is determined on first port and mlx4 device
+	 * which can potentially have two different link type for the same
+	 * IB device is considered as better to be avoided in the future,
+	 */
+	port = rdma_start_port(device);
+	if (rdma_cap_opa_mad(device, port))
+		ret = nla_put_string(msg, RDMA_NLDEV_ATTR_DEV_PROTOCOL, "opa");
+	else if (rdma_protocol_ib(device, port))
+		ret = nla_put_string(msg, RDMA_NLDEV_ATTR_DEV_PROTOCOL, "ib");
+	else if (rdma_protocol_iwarp(device, port))
+		ret = nla_put_string(msg, RDMA_NLDEV_ATTR_DEV_PROTOCOL, "iw");
+	else if (rdma_protocol_roce(device, port))
+		ret = nla_put_string(msg, RDMA_NLDEV_ATTR_DEV_PROTOCOL, "roce");
+	else if (rdma_protocol_usnic(device, port))
+		ret = nla_put_string(msg, RDMA_NLDEV_ATTR_DEV_PROTOCOL,
+				     "usnic");
+	return ret;
 }
 
 static int fill_port_info(struct sk_buff *msg,
diff --git a/include/uapi/rdma/rdma_netlink.h b/include/uapi/rdma/rdma_netlink.h
index 3a231a989974..d49f491341f6 100644
--- a/include/uapi/rdma/rdma_netlink.h
+++ b/include/uapi/rdma/rdma_netlink.h
@@ -470,6 +470,11 @@ enum rdma_nldev_attr {
 	 */
 	RDMA_NLDEV_SYS_ATTR_NETNS_MODE,		/* u8 */
 
+	/*
+	 * Device protocol, e.g. ib, iw, usnic, roce and opa
+	 */
+	RDMA_NLDEV_ATTR_DEV_PROTOCOL,		/* string */
+
 	/*
 	 * Always the end
 	 */
-- 
cgit v1.2.3-59-g8ed1b


From 2e5b8a01165e4fe57ec396961daae38713edce35 Mon Sep 17 00:00:00 2001
From: Parav Pandit <parav@mellanox.com>
Date: Mon, 15 Apr 2019 13:22:51 +0300
Subject: RDMA/core: Add a netlink command to change net namespace of rdma
 device

Provide an option to change the net namespace of a rdma device through a
netlink command. When multiple rdma devices exists in a system, and when
containers are used, this will limit rdma device visibility to a specified
net namespace.

An example command to change net namespace of mlx5_1 device to the
previously created net namespace 'foo' is:

$ ip netns add foo
$ rdma dev set mlx5_1 netns foo

Signed-off-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
---
 drivers/infiniband/core/core_priv.h |  2 ++
 drivers/infiniband/core/device.c    | 56 +++++++++++++++++++++++++++++++++----
 drivers/infiniband/core/nldev.c     | 13 ++++++++-
 include/uapi/rdma/rdma_netlink.h    |  6 +++-
 4 files changed, 70 insertions(+), 7 deletions(-)

(limited to 'include/uapi')

diff --git a/drivers/infiniband/core/core_priv.h b/drivers/infiniband/core/core_priv.h
index 5b0ffbb6b3c9..d4dd360769cb 100644
--- a/drivers/infiniband/core/core_priv.h
+++ b/drivers/infiniband/core/core_priv.h
@@ -350,4 +350,6 @@ int ib_port_register_module_stat(struct ib_device *device, u8 port_num,
 				 const char *name);
 void ib_port_unregister_module_stat(struct kobject *kobj);
 
+int ib_device_set_netns_put(struct sk_buff *skb,
+			    struct ib_device *dev, u32 ns_fd);
 #endif /* _CORE_PRIV_H */
diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index 7fe4f8b880ee..fcbf2d4c865d 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -1452,9 +1452,9 @@ static int rdma_dev_change_netns(struct ib_device *device, struct net *cur_net,
 	mutex_lock(&device->unregistration_lock);
 
 	/*
-	 * If a device not under ib_device_get() or the unregistration_lock
-	 * the namespace can be changed, or it can be unregistered. Check
-	 * again under the lock.
+	 * If a device not under ib_device_get() or if the unregistration_lock
+	 * is not held, the namespace can be changed, or it can be unregistered.
+	 * Check again under the lock.
 	 */
 	if (refcount_read(&device->refcount) == 0 ||
 	    !net_eq(cur_net, read_pnet(&device->coredev.rdma_net))) {
@@ -1471,12 +1471,12 @@ static int rdma_dev_change_netns(struct ib_device *device, struct net *cur_net,
 	 */
 	write_pnet(&device->coredev.rdma_net, net);
 
+	down_read(&devices_rwsem);
 	/*
 	 * Currently rdma devices are system wide unique. So the device name
 	 * is guaranteed free in the new namespace. Publish the new namespace
 	 * at the sysfs level.
 	 */
-	down_read(&devices_rwsem);
 	ret = device_rename(&device->dev, dev_name(&device->dev));
 	up_read(&devices_rwsem);
 	if (ret) {
@@ -1488,7 +1488,7 @@ static int rdma_dev_change_netns(struct ib_device *device, struct net *cur_net,
 	}
 
 	ret2 = enable_device_and_get(device);
-	if (ret2)
+	if (ret2) {
 		/*
 		 * This shouldn't really happen, but if it does, let the user
 		 * retry at later point. So don't disable the device.
@@ -1496,7 +1496,9 @@ static int rdma_dev_change_netns(struct ib_device *device, struct net *cur_net,
 		dev_warn(&device->dev,
 			 "%s: Couldn't re-enable device after namespace change\n",
 			 __func__);
+	}
 	kobject_uevent(&device->dev.kobj, KOBJ_ADD);
+
 	ib_device_put(device);
 out:
 	mutex_unlock(&device->unregistration_lock);
@@ -1505,6 +1507,50 @@ out:
 	return ret2;
 }
 
+int ib_device_set_netns_put(struct sk_buff *skb,
+			    struct ib_device *dev, u32 ns_fd)
+{
+	struct net *net;
+	int ret;
+
+	net = get_net_ns_by_fd(ns_fd);
+	if (IS_ERR(net)) {
+		ret = PTR_ERR(net);
+		goto net_err;
+	}
+
+	if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) {
+		ret = -EPERM;
+		goto ns_err;
+	}
+
+	/*
+	 * Currently supported only for those providers which support
+	 * disassociation and don't do port specific sysfs init. Once a
+	 * port_cleanup infrastructure is implemented, this limitation will be
+	 * removed.
+	 */
+	if (!dev->ops.disassociate_ucontext || dev->ops.init_port ||
+	    ib_devices_shared_netns) {
+		ret = -EOPNOTSUPP;
+		goto ns_err;
+	}
+
+	get_device(&dev->dev);
+	ib_device_put(dev);
+	ret = rdma_dev_change_netns(dev, current->nsproxy->net_ns, net);
+	put_device(&dev->dev);
+
+	put_net(net);
+	return ret;
+
+ns_err:
+	put_net(net);
+net_err:
+	ib_device_put(dev);
+	return ret;
+}
+
 static struct pernet_operations rdma_dev_net_ops = {
 	.init = rdma_dev_init_net,
 	.exit = rdma_dev_exit_net,
diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c
index 8cb3851d212e..bced945a456d 100644
--- a/drivers/infiniband/core/nldev.c
+++ b/drivers/infiniband/core/nldev.c
@@ -119,6 +119,7 @@ static const struct nla_policy nldev_policy[RDMA_NLDEV_ATTR_MAX] = {
 	[RDMA_NLDEV_SYS_ATTR_NETNS_MODE]	= { .type = NLA_U8 },
 	[RDMA_NLDEV_ATTR_DEV_PROTOCOL]		= { .type = NLA_NUL_STRING,
 				    .len = RDMA_NLDEV_ATTR_ENTRY_STRLEN },
+	[RDMA_NLDEV_NET_NS_FD]			= { .type = NLA_U32 },
 };
 
 static int put_driver_name_print_type(struct sk_buff *msg, const char *name,
@@ -691,9 +692,20 @@ static int nldev_set_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
 		nla_strlcpy(name, tb[RDMA_NLDEV_ATTR_DEV_NAME],
 			    IB_DEVICE_NAME_MAX);
 		err = ib_device_rename(device, name);
+		goto done;
 	}
 
+	if (tb[RDMA_NLDEV_NET_NS_FD]) {
+		u32 ns_fd;
+
+		ns_fd = nla_get_u32(tb[RDMA_NLDEV_NET_NS_FD]);
+		err = ib_device_set_netns_put(skb, device, ns_fd);
+		goto put_done;
+	}
+
+done:
 	ib_device_put(device);
+put_done:
 	return err;
 }
 
@@ -909,7 +921,6 @@ static int _nldev_res_get_dumpit(struct ib_device *device,
 		nlmsg_cancel(skb, nlh);
 		goto out;
 	}
-
 	nlmsg_end(skb, nlh);
 
 	idx++;
diff --git a/include/uapi/rdma/rdma_netlink.h b/include/uapi/rdma/rdma_netlink.h
index d49f491341f6..42a8bdc40a14 100644
--- a/include/uapi/rdma/rdma_netlink.h
+++ b/include/uapi/rdma/rdma_netlink.h
@@ -469,12 +469,16 @@ enum rdma_nldev_attr {
 	 * either shared or exclusive among multiple net namespaces.
 	 */
 	RDMA_NLDEV_SYS_ATTR_NETNS_MODE,		/* u8 */
-
 	/*
 	 * Device protocol, e.g. ib, iw, usnic, roce and opa
 	 */
 	RDMA_NLDEV_ATTR_DEV_PROTOCOL,		/* string */
 
+	/*
+	 * File descriptor handle of the net namespace object
+	 */
+	RDMA_NLDEV_NET_NS_FD,			/* u32 */
+
 	/*
 	 * Always the end
 	 */
-- 
cgit v1.2.3-59-g8ed1b


From 52438be4411271c5e93da54da340c3566b0e4bef Mon Sep 17 00:00:00 2001
From: Mark Bloch <markb@mellanox.com>
Date: Thu, 28 Mar 2019 15:46:23 +0200
Subject: RDMA/mlx5: Allow inserting a steering rule to the FDB

Allow this only via mlx5 raw create flow API, legacy verbs are not
supported. To accommodate that, we add a new attribute to matcher creation
to indicate the type of flow table to be used.
	MLX5_IB_ATTR_FLOW_MATCHER_FT_TYPE
With this new attribute MLX5_IB_ATTR_FLOW_MATCHER_FLOW_FLAGS is no longer
needed, we keep it for compatibility but at most only a single attribute can
be passed of the two.

When inserting a flow rule to the FDB we require that a DEVX FT is
provided as a destination, no other configuration is allowed.

Signed-off-by: Mark Bloch <markb@mellanox.com>
Reviewed-by: Maor Gottlieb <maorg@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
---
 drivers/infiniband/hw/mlx5/flow.c         | 75 ++++++++++++++++++++++++++-----
 include/uapi/rdma/mlx5_user_ioctl_cmds.h  |  1 +
 include/uapi/rdma/mlx5_user_ioctl_verbs.h |  1 +
 3 files changed, 65 insertions(+), 12 deletions(-)

(limited to 'include/uapi')

diff --git a/drivers/infiniband/hw/mlx5/flow.c b/drivers/infiniband/hw/mlx5/flow.c
index 09f5bc6142c9..71a8d46a0827 100644
--- a/drivers/infiniband/hw/mlx5/flow.c
+++ b/drivers/infiniband/hw/mlx5/flow.c
@@ -29,6 +29,9 @@ mlx5_ib_ft_type_to_namespace(enum mlx5_ib_uapi_flow_table_type table_type,
 	case MLX5_IB_UAPI_FLOW_TABLE_TYPE_NIC_TX:
 		*namespace = MLX5_FLOW_NAMESPACE_EGRESS;
 		break;
+	case MLX5_IB_UAPI_FLOW_TABLE_TYPE_FDB:
+		*namespace = MLX5_FLOW_NAMESPACE_FDB;
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -93,6 +96,10 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_CREATE_FLOW)(
 	    ((dest_devx && dest_qp) || (!dest_devx && !dest_qp)))
 		return -EINVAL;
 
+	/* Allow only DEVX object as dest when inserting to FDB */
+	if (fs_matcher->ns_type == MLX5_FLOW_NAMESPACE_FDB && !dest_devx)
+		return -EINVAL;
+
 	if (dest_devx) {
 		devx_obj = uverbs_attr_get_obj(
 			attrs, MLX5_IB_ATTR_CREATE_FLOW_DEST_DEVX);
@@ -104,6 +111,10 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_CREATE_FLOW)(
 		 */
 		if (!mlx5_ib_devx_is_flow_dest(devx_obj, &dest_id, &dest_type))
 			return -EINVAL;
+		/* Allow only flow table as dest when inserting to FDB */
+		if (fs_matcher->ns_type == MLX5_FLOW_NAMESPACE_FDB &&
+		    dest_type != MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE)
+			return -EINVAL;
 	} else if (dest_qp) {
 		struct mlx5_ib_qp *mqp;
 
@@ -203,6 +214,54 @@ static int flow_matcher_cleanup(struct ib_uobject *uobject,
 	return 0;
 }
 
+static int mlx5_ib_matcher_ns(struct uverbs_attr_bundle *attrs,
+			      struct mlx5_ib_flow_matcher *obj)
+{
+	enum mlx5_ib_uapi_flow_table_type ft_type =
+		MLX5_IB_UAPI_FLOW_TABLE_TYPE_NIC_RX;
+	u32 flags;
+	int err;
+
+	/* New users should use MLX5_IB_ATTR_FLOW_MATCHER_FT_TYPE and older
+	 * users should switch to it. We leave this to not break userspace
+	 */
+	if (uverbs_attr_is_valid(attrs, MLX5_IB_ATTR_FLOW_MATCHER_FT_TYPE) &&
+	    uverbs_attr_is_valid(attrs, MLX5_IB_ATTR_FLOW_MATCHER_FLOW_FLAGS))
+		return -EINVAL;
+
+	if (uverbs_attr_is_valid(attrs, MLX5_IB_ATTR_FLOW_MATCHER_FT_TYPE)) {
+		err = uverbs_get_const(&ft_type, attrs,
+				       MLX5_IB_ATTR_FLOW_MATCHER_FT_TYPE);
+		if (err)
+			return err;
+
+		err = mlx5_ib_ft_type_to_namespace(ft_type, &obj->ns_type);
+		if (err)
+			return err;
+
+		return 0;
+	}
+
+	if (uverbs_attr_is_valid(attrs, MLX5_IB_ATTR_FLOW_MATCHER_FLOW_FLAGS)) {
+		err = uverbs_get_flags32(&flags, attrs,
+					 MLX5_IB_ATTR_FLOW_MATCHER_FLOW_FLAGS,
+					 IB_FLOW_ATTR_FLAGS_EGRESS);
+		if (err)
+			return err;
+
+		if (flags) {
+			mlx5_ib_ft_type_to_namespace(
+				MLX5_IB_UAPI_FLOW_TABLE_TYPE_NIC_TX,
+				&obj->ns_type);
+			return 0;
+		}
+	}
+
+	obj->ns_type = MLX5_FLOW_NAMESPACE_BYPASS;
+
+	return 0;
+}
+
 static int UVERBS_HANDLER(MLX5_IB_METHOD_FLOW_MATCHER_CREATE)(
 	struct uverbs_attr_bundle *attrs)
 {
@@ -210,14 +269,12 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_FLOW_MATCHER_CREATE)(
 		attrs, MLX5_IB_ATTR_FLOW_MATCHER_CREATE_HANDLE);
 	struct mlx5_ib_dev *dev = mlx5_udata_to_mdev(&attrs->driver_udata);
 	struct mlx5_ib_flow_matcher *obj;
-	u32 flags;
 	int err;
 
 	obj = kzalloc(sizeof(struct mlx5_ib_flow_matcher), GFP_KERNEL);
 	if (!obj)
 		return -ENOMEM;
 
-	obj->ns_type = MLX5_FLOW_NAMESPACE_BYPASS;
 	obj->mask_len = uverbs_attr_get_len(
 		attrs, MLX5_IB_ATTR_FLOW_MATCHER_MATCH_MASK);
 	err = uverbs_copy_from(&obj->matcher_mask,
@@ -243,19 +300,10 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_FLOW_MATCHER_CREATE)(
 	if (err)
 		goto end;
 
-	err = uverbs_get_flags32(&flags, attrs,
-				 MLX5_IB_ATTR_FLOW_MATCHER_FLOW_FLAGS,
-				 IB_FLOW_ATTR_FLAGS_EGRESS);
+	err = mlx5_ib_matcher_ns(attrs, obj);
 	if (err)
 		goto end;
 
-	if (flags) {
-		err = mlx5_ib_ft_type_to_namespace(
-			MLX5_IB_UAPI_FLOW_TABLE_TYPE_NIC_TX, &obj->ns_type);
-		if (err)
-			goto end;
-	}
-
 	uobj->object = obj;
 	obj->mdev = dev->mdev;
 	atomic_set(&obj->usecnt, 0);
@@ -605,6 +653,9 @@ DECLARE_UVERBS_NAMED_METHOD(
 			   UA_MANDATORY),
 	UVERBS_ATTR_FLAGS_IN(MLX5_IB_ATTR_FLOW_MATCHER_FLOW_FLAGS,
 			     enum ib_flow_flags,
+			     UA_OPTIONAL),
+	UVERBS_ATTR_CONST_IN(MLX5_IB_ATTR_FLOW_MATCHER_FT_TYPE,
+			     enum mlx5_ib_uapi_flow_table_type,
 			     UA_OPTIONAL));
 
 DECLARE_UVERBS_NAMED_METHOD_DESTROY(
diff --git a/include/uapi/rdma/mlx5_user_ioctl_cmds.h b/include/uapi/rdma/mlx5_user_ioctl_cmds.h
index 8149d224030b..0d8f564ce60b 100644
--- a/include/uapi/rdma/mlx5_user_ioctl_cmds.h
+++ b/include/uapi/rdma/mlx5_user_ioctl_cmds.h
@@ -144,6 +144,7 @@ enum mlx5_ib_flow_matcher_create_attrs {
 	MLX5_IB_ATTR_FLOW_MATCHER_FLOW_TYPE,
 	MLX5_IB_ATTR_FLOW_MATCHER_MATCH_CRITERIA,
 	MLX5_IB_ATTR_FLOW_MATCHER_FLOW_FLAGS,
+	MLX5_IB_ATTR_FLOW_MATCHER_FT_TYPE,
 };
 
 enum mlx5_ib_flow_matcher_destroy_attrs {
diff --git a/include/uapi/rdma/mlx5_user_ioctl_verbs.h b/include/uapi/rdma/mlx5_user_ioctl_verbs.h
index 4a701033b93f..0a126a6b9337 100644
--- a/include/uapi/rdma/mlx5_user_ioctl_verbs.h
+++ b/include/uapi/rdma/mlx5_user_ioctl_verbs.h
@@ -42,6 +42,7 @@ enum mlx5_ib_uapi_flow_action_flags {
 enum mlx5_ib_uapi_flow_table_type {
 	MLX5_IB_UAPI_FLOW_TABLE_TYPE_NIC_RX     = 0x0,
 	MLX5_IB_UAPI_FLOW_TABLE_TYPE_NIC_TX	= 0x1,
+	MLX5_IB_UAPI_FLOW_TABLE_TYPE_FDB	= 0x2,
 };
 
 enum mlx5_ib_uapi_flow_action_packet_reformat_type {
-- 
cgit v1.2.3-59-g8ed1b


From 1f1d6abbf0bebe4b1fc33b80730a1b4bfbc8f7bb Mon Sep 17 00:00:00 2001
From: Ariel Levkovich <lariel@mellanox.com>
Date: Sun, 31 Mar 2019 19:44:50 +0300
Subject: IB/mlx5: Expose TIR ICM address to user space

This patch exposes the TIR ICM address of raw packet and RSS
QPs to user space.

In order to pass the new field, the patch extends the mlx5
specific QP creation response structure and fills it with
the icm address returned by the FW command, if available.

Signed-off-by: Ariel Levkovich <lariel@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
---
 drivers/infiniband/hw/mlx5/qp.c | 46 ++++++++++++++++++++++++++++++++++++-----
 include/uapi/rdma/mlx5-abi.h    |  2 ++
 2 files changed, 43 insertions(+), 5 deletions(-)

(limited to 'include/uapi')

diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 19ae2b018f01..1af28bca9acd 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -1402,7 +1402,8 @@ static void destroy_raw_packet_qp_tir(struct mlx5_ib_dev *dev,
 static int create_raw_packet_qp_tir(struct mlx5_ib_dev *dev,
 				    struct mlx5_ib_rq *rq, u32 tdn,
 				    u32 *qp_flags_en,
-				    struct ib_pd *pd)
+				    struct ib_pd *pd,
+				    u32 *out, int outlen)
 {
 	u8 lb_flag = 0;
 	u32 *in;
@@ -1436,8 +1437,9 @@ static int create_raw_packet_qp_tir(struct mlx5_ib_dev *dev,
 
 	MLX5_SET(tirc, tirc, self_lb_block, lb_flag);
 
-	err = mlx5_core_create_tir(dev->mdev, in, inlen, &rq->tirn);
+	err = mlx5_core_create_tir_out(dev->mdev, in, inlen, out, outlen);
 
+	rq->tirn = MLX5_GET(create_tir_out, out, tirn);
 	if (!err && MLX5_GET(tirc, tirc, self_lb_block)) {
 		err = mlx5_ib_enable_lb(dev, false, true);
 
@@ -1463,6 +1465,7 @@ static int create_raw_packet_qp(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
 	int err;
 	u32 tdn = mucontext->tdn;
 	u16 uid = to_mpd(pd)->uid;
+	u32 out[MLX5_ST_SZ_DW(create_tir_out)] = {};
 
 	if (qp->sq.wqe_cnt) {
 		err = create_raw_packet_qp_tis(dev, qp, sq, tdn, pd);
@@ -1495,7 +1498,9 @@ static int create_raw_packet_qp(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
 		if (err)
 			goto err_destroy_sq;
 
-		err = create_raw_packet_qp_tir(dev, rq, tdn, &qp->flags_en, pd);
+		err = create_raw_packet_qp_tir(
+			dev, rq, tdn, &qp->flags_en, pd, out,
+			MLX5_ST_SZ_BYTES(create_tir_out));
 		if (err)
 			goto err_destroy_rq;
 
@@ -1504,6 +1509,20 @@ static int create_raw_packet_qp(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
 			resp->comp_mask |= MLX5_IB_CREATE_QP_RESP_MASK_RQN;
 			resp->tirn = rq->tirn;
 			resp->comp_mask |= MLX5_IB_CREATE_QP_RESP_MASK_TIRN;
+			if (MLX5_CAP_FLOWTABLE_NIC_RX(dev->mdev, sw_owner)) {
+				resp->tir_icm_addr = MLX5_GET(
+					create_tir_out, out, icm_address_31_0);
+				resp->tir_icm_addr |=
+					(u64)MLX5_GET(create_tir_out, out,
+						      icm_address_39_32)
+					<< 32;
+				resp->tir_icm_addr |=
+					(u64)MLX5_GET(create_tir_out, out,
+						      icm_address_63_40)
+					<< 40;
+				resp->comp_mask |=
+					MLX5_IB_CREATE_QP_RESP_MASK_TIR_ICM_ADDR;
+			}
 		}
 	}
 
@@ -1577,8 +1596,10 @@ static int create_rss_raw_qp_tir(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
 		udata, struct mlx5_ib_ucontext, ibucontext);
 	struct mlx5_ib_create_qp_resp resp = {};
 	int inlen;
+	int outlen;
 	int err;
 	u32 *in;
+	u32 *out;
 	void *tirc;
 	void *hfso;
 	u32 selected_fields = 0;
@@ -1658,10 +1679,12 @@ static int create_rss_raw_qp_tir(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
 	}
 
 	inlen = MLX5_ST_SZ_BYTES(create_tir_in);
-	in = kvzalloc(inlen, GFP_KERNEL);
+	outlen = MLX5_ST_SZ_BYTES(create_tir_out);
+	in = kvzalloc(inlen + outlen, GFP_KERNEL);
 	if (!in)
 		return -ENOMEM;
 
+	out = in + MLX5_ST_SZ_DW(create_tir_in);
 	MLX5_SET(create_tir_in, in, uid, to_mpd(pd)->uid);
 	tirc = MLX5_ADDR_OF(create_tir_in, in, ctx);
 	MLX5_SET(tirc, tirc, disp_type,
@@ -1773,8 +1796,9 @@ static int create_rss_raw_qp_tir(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
 	MLX5_SET(rx_hash_field_select, hfso, selected_fields, selected_fields);
 
 create_tir:
-	err = mlx5_core_create_tir(dev->mdev, in, inlen, &qp->rss_qp.tirn);
+	err = mlx5_core_create_tir_out(dev->mdev, in, inlen, out, outlen);
 
+	qp->rss_qp.tirn = MLX5_GET(create_tir_out, out, tirn);
 	if (!err && MLX5_GET(tirc, tirc, self_lb_block)) {
 		err = mlx5_ib_enable_lb(dev, false, true);
 
@@ -1789,6 +1813,18 @@ create_tir:
 	if (mucontext->devx_uid) {
 		resp.comp_mask |= MLX5_IB_CREATE_QP_RESP_MASK_TIRN;
 		resp.tirn = qp->rss_qp.tirn;
+		if (MLX5_CAP_FLOWTABLE_NIC_RX(dev->mdev, sw_owner)) {
+			resp.tir_icm_addr =
+				MLX5_GET(create_tir_out, out, icm_address_31_0);
+			resp.tir_icm_addr |= (u64)MLX5_GET(create_tir_out, out,
+							   icm_address_39_32)
+					     << 32;
+			resp.tir_icm_addr |= (u64)MLX5_GET(create_tir_out, out,
+							   icm_address_63_40)
+					     << 40;
+			resp.comp_mask |=
+				MLX5_IB_CREATE_QP_RESP_MASK_TIR_ICM_ADDR;
+		}
 	}
 
 	err = ib_copy_to_udata(udata, &resp, min(udata->outlen, sizeof(resp)));
diff --git a/include/uapi/rdma/mlx5-abi.h b/include/uapi/rdma/mlx5-abi.h
index 87b3198f4b5d..0ef404f75f56 100644
--- a/include/uapi/rdma/mlx5-abi.h
+++ b/include/uapi/rdma/mlx5-abi.h
@@ -359,6 +359,7 @@ enum mlx5_ib_create_qp_resp_mask {
 	MLX5_IB_CREATE_QP_RESP_MASK_TISN = 1UL << 1,
 	MLX5_IB_CREATE_QP_RESP_MASK_RQN  = 1UL << 2,
 	MLX5_IB_CREATE_QP_RESP_MASK_SQN  = 1UL << 3,
+	MLX5_IB_CREATE_QP_RESP_MASK_TIR_ICM_ADDR  = 1UL << 4,
 };
 
 struct mlx5_ib_create_qp_resp {
@@ -370,6 +371,7 @@ struct mlx5_ib_create_qp_resp {
 	__u32	rqn;
 	__u32	sqn;
 	__u32   reserved1;
+	__u64	tir_icm_addr;
 };
 
 struct mlx5_ib_alloc_mw {
-- 
cgit v1.2.3-59-g8ed1b


From 3b113a1ec3d4ac7e1e621b77650ac05491f5924a Mon Sep 17 00:00:00 2001
From: Ariel Levkovich <lariel@mellanox.com>
Date: Sun, 5 May 2019 17:07:11 +0300
Subject: IB/mlx5: Support device memory type attribute

This patch intoruduces a new mlx5_ib driver attribute to the DM allocation
method - the DM type.

In order to allow addition of new types in downstream patches this patch
also refactors the allocation, deallocation and registration handlers to
consider the requested type and perform the necessary actions according to
it.

Since not all future device memory types will be such that are mapped to
user memory, the mandatory page index output attribute is modified to be
optional.

Signed-off-by: Ariel Levkovich <lariel@mellanox.com>
Reviewed-by: Eli Cohen <eli@mellanox.com>
Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
---
 drivers/infiniband/hw/mlx5/cmd.c          |  30 +++----
 drivers/infiniband/hw/mlx5/cmd.h          |   4 +-
 drivers/infiniband/hw/mlx5/main.c         | 135 +++++++++++++++++++-----------
 drivers/infiniband/hw/mlx5/mlx5_ib.h      |  23 +++--
 drivers/infiniband/hw/mlx5/mr.c           |  32 ++++---
 include/uapi/rdma/mlx5_user_ioctl_cmds.h  |   1 +
 include/uapi/rdma/mlx5_user_ioctl_verbs.h |   4 +
 7 files changed, 145 insertions(+), 84 deletions(-)

(limited to 'include/uapi')

diff --git a/drivers/infiniband/hw/mlx5/cmd.c b/drivers/infiniband/hw/mlx5/cmd.c
index be95ac5aeb30..f0e9c7609083 100644
--- a/drivers/infiniband/hw/mlx5/cmd.c
+++ b/drivers/infiniband/hw/mlx5/cmd.c
@@ -82,10 +82,10 @@ int mlx5_cmd_modify_cong_params(struct mlx5_core_dev *dev,
 	return mlx5_cmd_exec(dev, in, in_size, out, sizeof(out));
 }
 
-int mlx5_cmd_alloc_memic(struct mlx5_memic *memic, phys_addr_t *addr,
-			  u64 length, u32 alignment)
+int mlx5_cmd_alloc_memic(struct mlx5_dm *dm, phys_addr_t *addr,
+			 u64 length, u32 alignment)
 {
-	struct mlx5_core_dev *dev = memic->dev;
+	struct mlx5_core_dev *dev = dm->dev;
 	u64 num_memic_hw_pages = MLX5_CAP_DEV_MEM(dev, memic_bar_size)
 					>> PAGE_SHIFT;
 	u64 hw_start_addr = MLX5_CAP64_DEV_MEM(dev, memic_bar_start_addr);
@@ -115,17 +115,17 @@ int mlx5_cmd_alloc_memic(struct mlx5_memic *memic, phys_addr_t *addr,
 		 mlx5_alignment);
 
 	while (page_idx < num_memic_hw_pages) {
-		spin_lock(&memic->memic_lock);
-		page_idx = bitmap_find_next_zero_area(memic->memic_alloc_pages,
+		spin_lock(&dm->lock);
+		page_idx = bitmap_find_next_zero_area(dm->memic_alloc_pages,
 						      num_memic_hw_pages,
 						      page_idx,
 						      num_pages, 0);
 
 		if (page_idx < num_memic_hw_pages)
-			bitmap_set(memic->memic_alloc_pages,
+			bitmap_set(dm->memic_alloc_pages,
 				   page_idx, num_pages);
 
-		spin_unlock(&memic->memic_lock);
+		spin_unlock(&dm->lock);
 
 		if (page_idx >= num_memic_hw_pages)
 			break;
@@ -135,10 +135,10 @@ int mlx5_cmd_alloc_memic(struct mlx5_memic *memic, phys_addr_t *addr,
 
 		ret = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
 		if (ret) {
-			spin_lock(&memic->memic_lock);
-			bitmap_clear(memic->memic_alloc_pages,
+			spin_lock(&dm->lock);
+			bitmap_clear(dm->memic_alloc_pages,
 				     page_idx, num_pages);
-			spin_unlock(&memic->memic_lock);
+			spin_unlock(&dm->lock);
 
 			if (ret == -EAGAIN) {
 				page_idx++;
@@ -157,9 +157,9 @@ int mlx5_cmd_alloc_memic(struct mlx5_memic *memic, phys_addr_t *addr,
 	return -ENOMEM;
 }
 
-int mlx5_cmd_dealloc_memic(struct mlx5_memic *memic, u64 addr, u64 length)
+int mlx5_cmd_dealloc_memic(struct mlx5_dm *dm, u64 addr, u64 length)
 {
-	struct mlx5_core_dev *dev = memic->dev;
+	struct mlx5_core_dev *dev = dm->dev;
 	u64 hw_start_addr = MLX5_CAP64_DEV_MEM(dev, memic_bar_start_addr);
 	u32 num_pages = DIV_ROUND_UP(length, PAGE_SIZE);
 	u32 out[MLX5_ST_SZ_DW(dealloc_memic_out)] = {0};
@@ -177,10 +177,10 @@ int mlx5_cmd_dealloc_memic(struct mlx5_memic *memic, u64 addr, u64 length)
 	err =  mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
 
 	if (!err) {
-		spin_lock(&memic->memic_lock);
-		bitmap_clear(memic->memic_alloc_pages,
+		spin_lock(&dm->lock);
+		bitmap_clear(dm->memic_alloc_pages,
 			     start_page_idx, num_pages);
-		spin_unlock(&memic->memic_lock);
+		spin_unlock(&dm->lock);
 	}
 
 	return err;
diff --git a/drivers/infiniband/hw/mlx5/cmd.h b/drivers/infiniband/hw/mlx5/cmd.h
index 923a7b93f507..80a644bea6c7 100644
--- a/drivers/infiniband/hw/mlx5/cmd.h
+++ b/drivers/infiniband/hw/mlx5/cmd.h
@@ -44,9 +44,9 @@ int mlx5_cmd_query_cong_params(struct mlx5_core_dev *dev, int cong_point,
 int mlx5_cmd_query_ext_ppcnt_counters(struct mlx5_core_dev *dev, void *out);
 int mlx5_cmd_modify_cong_params(struct mlx5_core_dev *mdev,
 				void *in, int in_size);
-int mlx5_cmd_alloc_memic(struct mlx5_memic *memic, phys_addr_t *addr,
+int mlx5_cmd_alloc_memic(struct mlx5_dm *dm, phys_addr_t *addr,
 			 u64 length, u32 alignment);
-int mlx5_cmd_dealloc_memic(struct mlx5_memic *memic, u64 addr, u64 length);
+int mlx5_cmd_dealloc_memic(struct mlx5_dm *dm, u64 addr, u64 length);
 void mlx5_cmd_dealloc_pd(struct mlx5_core_dev *dev, u32 pdn, u16 uid);
 void mlx5_cmd_destroy_tir(struct mlx5_core_dev *dev, u32 tirn, u16 uid);
 void mlx5_cmd_destroy_tis(struct mlx5_core_dev *dev, u32 tisn, u16 uid);
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 5ac24bce6e77..97f32a03e456 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -2264,58 +2264,90 @@ static int mlx5_ib_mmap(struct ib_ucontext *ibcontext, struct vm_area_struct *vm
 	return 0;
 }
 
-struct ib_dm *mlx5_ib_alloc_dm(struct ib_device *ibdev,
-			       struct ib_ucontext *context,
-			       struct ib_dm_alloc_attr *attr,
-			       struct uverbs_attr_bundle *attrs)
+static int handle_alloc_dm_memic(struct ib_ucontext *ctx,
+				 struct mlx5_ib_dm *dm,
+				 struct ib_dm_alloc_attr *attr,
+				 struct uverbs_attr_bundle *attrs)
 {
-	u64 act_size = roundup(attr->length, MLX5_MEMIC_BASE_SIZE);
-	struct mlx5_memic *memic = &to_mdev(ibdev)->memic;
-	phys_addr_t memic_addr;
-	struct mlx5_ib_dm *dm;
+	struct mlx5_dm *dm_db = &to_mdev(ctx->device)->dm;
 	u64 start_offset;
 	u32 page_idx;
 	int err;
 
-	dm = kzalloc(sizeof(*dm), GFP_KERNEL);
-	if (!dm)
-		return ERR_PTR(-ENOMEM);
-
-	mlx5_ib_dbg(to_mdev(ibdev), "alloc_memic req: user_length=0x%llx act_length=0x%llx log_alignment=%d\n",
-		    attr->length, act_size, attr->alignment);
+	dm->size = roundup(attr->length, MLX5_MEMIC_BASE_SIZE);
 
-	err = mlx5_cmd_alloc_memic(memic, &memic_addr,
-				   act_size, attr->alignment);
+	err = mlx5_cmd_alloc_memic(dm_db, &dm->dev_addr,
+				   dm->size, attr->alignment);
 	if (err)
-		goto err_free;
+		return err;
 
-	start_offset = memic_addr & ~PAGE_MASK;
-	page_idx = (memic_addr - memic->dev->bar_addr -
-		    MLX5_CAP64_DEV_MEM(memic->dev, memic_bar_start_addr)) >>
+	page_idx = (dm->dev_addr - pci_resource_start(dm_db->dev->pdev, 0) -
+		    MLX5_CAP64_DEV_MEM(dm_db->dev, memic_bar_start_addr)) >>
 		    PAGE_SHIFT;
 
 	err = uverbs_copy_to(attrs,
-			     MLX5_IB_ATTR_ALLOC_DM_RESP_START_OFFSET,
-			     &start_offset, sizeof(start_offset));
+			     MLX5_IB_ATTR_ALLOC_DM_RESP_PAGE_INDEX,
+			     &page_idx, sizeof(page_idx));
 	if (err)
 		goto err_dealloc;
 
+	start_offset = dm->dev_addr & ~PAGE_MASK;
 	err = uverbs_copy_to(attrs,
-			     MLX5_IB_ATTR_ALLOC_DM_RESP_PAGE_INDEX,
-			     &page_idx, sizeof(page_idx));
+			     MLX5_IB_ATTR_ALLOC_DM_RESP_START_OFFSET,
+			     &start_offset, sizeof(start_offset));
 	if (err)
 		goto err_dealloc;
 
-	bitmap_set(to_mucontext(context)->dm_pages, page_idx,
-		   DIV_ROUND_UP(act_size, PAGE_SIZE));
+	bitmap_set(to_mucontext(ctx)->dm_pages, page_idx,
+		   DIV_ROUND_UP(dm->size, PAGE_SIZE));
+
+	return 0;
+
+err_dealloc:
+	mlx5_cmd_dealloc_memic(dm_db, dm->dev_addr, dm->size);
+
+	return err;
+}
+
+struct ib_dm *mlx5_ib_alloc_dm(struct ib_device *ibdev,
+			       struct ib_ucontext *context,
+			       struct ib_dm_alloc_attr *attr,
+			       struct uverbs_attr_bundle *attrs)
+{
+	struct mlx5_ib_dm *dm;
+	enum mlx5_ib_uapi_dm_type type;
+	int err;
+
+	err = uverbs_get_const_default(&type, attrs,
+				       MLX5_IB_ATTR_ALLOC_DM_REQ_TYPE,
+				       MLX5_IB_UAPI_DM_TYPE_MEMIC);
+	if (err)
+		return ERR_PTR(err);
+
+	mlx5_ib_dbg(to_mdev(ibdev), "alloc_dm req: dm_type=%d user_length=0x%llx log_alignment=%d\n",
+		    type, attr->length, attr->alignment);
+
+	dm = kzalloc(sizeof(*dm), GFP_KERNEL);
+	if (!dm)
+		return ERR_PTR(-ENOMEM);
+
+	dm->type = type;
+
+	switch (type) {
+	case MLX5_IB_UAPI_DM_TYPE_MEMIC:
+		err = handle_alloc_dm_memic(context, dm,
+					    attr,
+					    attrs);
+		break;
+	default:
+		err = -EOPNOTSUPP;
+	}
 
-	dm->dev_addr = memic_addr;
+	if (err)
+		goto err_free;
 
 	return &dm->ibdm;
 
-err_dealloc:
-	mlx5_cmd_dealloc_memic(memic, memic_addr,
-			       act_size);
 err_free:
 	kfree(dm);
 	return ERR_PTR(err);
@@ -2323,25 +2355,31 @@ err_free:
 
 int mlx5_ib_dealloc_dm(struct ib_dm *ibdm, struct uverbs_attr_bundle *attrs)
 {
-	struct mlx5_memic *memic = &to_mdev(ibdm->device)->memic;
+	struct mlx5_dm *dm_db = &to_mdev(ibdm->device)->dm;
 	struct mlx5_ib_dm *dm = to_mdm(ibdm);
-	u64 act_size = roundup(dm->ibdm.length, MLX5_MEMIC_BASE_SIZE);
 	u32 page_idx;
 	int ret;
 
-	ret = mlx5_cmd_dealloc_memic(memic, dm->dev_addr, act_size);
-	if (ret)
-		return ret;
+	switch (dm->type) {
+	case MLX5_IB_UAPI_DM_TYPE_MEMIC:
+		ret = mlx5_cmd_dealloc_memic(dm_db, dm->dev_addr, dm->size);
+		if (ret)
+			return ret;
 
-	page_idx = (dm->dev_addr - memic->dev->bar_addr -
-		    MLX5_CAP64_DEV_MEM(memic->dev, memic_bar_start_addr)) >>
-		    PAGE_SHIFT;
-	bitmap_clear(rdma_udata_to_drv_context(
-			&attrs->driver_udata,
-			struct mlx5_ib_ucontext,
-			ibucontext)->dm_pages,
-		     page_idx,
-		     DIV_ROUND_UP(act_size, PAGE_SIZE));
+		page_idx = (dm->dev_addr -
+			    pci_resource_start(dm_db->dev->pdev, 0) -
+			    MLX5_CAP64_DEV_MEM(dm_db->dev,
+					       memic_bar_start_addr)) >>
+			   PAGE_SHIFT;
+		bitmap_clear(rdma_udata_to_drv_context(&attrs->driver_udata,
+						       struct mlx5_ib_ucontext,
+						       ibucontext)
+				     ->dm_pages,
+			     page_idx, DIV_ROUND_UP(dm->size, PAGE_SIZE));
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
 
 	kfree(dm);
 
@@ -5768,7 +5806,10 @@ ADD_UVERBS_ATTRIBUTES_SIMPLE(
 			    UA_MANDATORY),
 	UVERBS_ATTR_PTR_OUT(MLX5_IB_ATTR_ALLOC_DM_RESP_PAGE_INDEX,
 			    UVERBS_ATTR_TYPE(u16),
-			    UA_MANDATORY));
+			    UA_OPTIONAL),
+	UVERBS_ATTR_CONST_IN(MLX5_IB_ATTR_ALLOC_DM_REQ_TYPE,
+			     enum mlx5_ib_uapi_dm_type,
+			     UA_OPTIONAL));
 
 ADD_UVERBS_ATTRIBUTES_SIMPLE(
 	mlx5_ib_flow_action,
@@ -5916,8 +5957,8 @@ static int mlx5_ib_stage_init_init(struct mlx5_ib_dev *dev)
 	INIT_LIST_HEAD(&dev->qp_list);
 	spin_lock_init(&dev->reset_flow_resource_lock);
 
-	spin_lock_init(&dev->memic.memic_lock);
-	dev->memic.dev = mdev;
+	spin_lock_init(&dev->dm.lock);
+	dev->dm.dev = mdev;
 
 	if (IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING)) {
 		err = init_srcu_struct(&dev->mr_srcu);
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index 55b8bdb402b6..714c360dc9fb 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -48,6 +48,7 @@
 #include <rdma/mlx5-abi.h>
 #include <rdma/uverbs_ioctl.h>
 #include <rdma/mlx5_user_ioctl_cmds.h>
+#include <rdma/mlx5_user_ioctl_verbs.h>
 
 #include "srq.h"
 
@@ -554,15 +555,17 @@ enum mlx5_ib_mtt_access_flags {
 struct mlx5_ib_dm {
 	struct ib_dm		ibdm;
 	phys_addr_t		dev_addr;
+	u32			type;
+	size_t			size;
 };
 
 #define MLX5_IB_MTT_PRESENT (MLX5_IB_MTT_READ | MLX5_IB_MTT_WRITE)
 
-#define MLX5_IB_DM_ALLOWED_ACCESS (IB_ACCESS_LOCAL_WRITE   |\
-				   IB_ACCESS_REMOTE_WRITE  |\
-				   IB_ACCESS_REMOTE_READ   |\
-				   IB_ACCESS_REMOTE_ATOMIC |\
-				   IB_ZERO_BASED)
+#define MLX5_IB_DM_MEMIC_ALLOWED_ACCESS (IB_ACCESS_LOCAL_WRITE   |\
+					 IB_ACCESS_REMOTE_WRITE  |\
+					 IB_ACCESS_REMOTE_READ   |\
+					 IB_ACCESS_REMOTE_ATOMIC |\
+					 IB_ZERO_BASED)
 
 struct mlx5_ib_mr {
 	struct ib_mr		ibmr;
@@ -843,9 +846,13 @@ struct mlx5_ib_flow_action {
 	};
 };
 
-struct mlx5_memic {
+struct mlx5_dm {
 	struct mlx5_core_dev *dev;
-	spinlock_t		memic_lock;
+	/* This lock is used to protect the access to the shared
+	 * allocation map when concurrent requests by different
+	 * processes are handled.
+	 */
+	spinlock_t lock;
 	DECLARE_BITMAP(memic_alloc_pages, MLX5_MAX_MEMIC_PAGES);
 };
 
@@ -949,7 +956,7 @@ struct mlx5_ib_dev {
 	u8			umr_fence;
 	struct list_head	ib_dev_list;
 	u64			sys_image_guid;
-	struct mlx5_memic	memic;
+	struct mlx5_dm		dm;
 	u16			devx_whitelist_uid;
 	struct mlx5_srq_table   srq_table;
 	struct mlx5_async_ctx   async_ctx;
diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index 4381cddab97b..ba35d68e7499 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -1159,8 +1159,8 @@ static void set_mr_fields(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr,
 	mr->access_flags = access_flags;
 }
 
-static struct ib_mr *mlx5_ib_get_memic_mr(struct ib_pd *pd, u64 memic_addr,
-					  u64 length, int acc)
+static struct ib_mr *mlx5_ib_get_dm_mr(struct ib_pd *pd, u64 start_addr,
+				       u64 length, int acc, int mode)
 {
 	struct mlx5_ib_dev *dev = to_mdev(pd->device);
 	int inlen = MLX5_ST_SZ_BYTES(create_mkey_in);
@@ -1182,9 +1182,8 @@ static struct ib_mr *mlx5_ib_get_memic_mr(struct ib_pd *pd, u64 memic_addr,
 
 	mkc = MLX5_ADDR_OF(create_mkey_in, in, memory_key_mkey_entry);
 
-	MLX5_SET(mkc, mkc, access_mode_1_0, MLX5_MKC_ACCESS_MODE_MEMIC & 0x3);
-	MLX5_SET(mkc, mkc, access_mode_4_2,
-		 (MLX5_MKC_ACCESS_MODE_MEMIC >> 2) & 0x7);
+	MLX5_SET(mkc, mkc, access_mode_1_0, mode & 0x3);
+	MLX5_SET(mkc, mkc, access_mode_4_2, (mode >> 2) & 0x7);
 	MLX5_SET(mkc, mkc, a, !!(acc & IB_ACCESS_REMOTE_ATOMIC));
 	MLX5_SET(mkc, mkc, rw, !!(acc & IB_ACCESS_REMOTE_WRITE));
 	MLX5_SET(mkc, mkc, rr, !!(acc & IB_ACCESS_REMOTE_READ));
@@ -1194,7 +1193,7 @@ static struct ib_mr *mlx5_ib_get_memic_mr(struct ib_pd *pd, u64 memic_addr,
 	MLX5_SET64(mkc, mkc, len, length);
 	MLX5_SET(mkc, mkc, pd, to_mpd(pd)->pdn);
 	MLX5_SET(mkc, mkc, qpn, 0xffffff);
-	MLX5_SET64(mkc, mkc, start_addr, memic_addr - dev->mdev->bar_addr);
+	MLX5_SET64(mkc, mkc, start_addr, start_addr);
 
 	err = mlx5_core_create_mkey(mdev, &mr->mmkey, in, inlen);
 	if (err)
@@ -1236,15 +1235,24 @@ struct ib_mr *mlx5_ib_reg_dm_mr(struct ib_pd *pd, struct ib_dm *dm,
 				struct uverbs_attr_bundle *attrs)
 {
 	struct mlx5_ib_dm *mdm = to_mdm(dm);
-	u64 memic_addr;
+	struct mlx5_core_dev *dev = to_mdev(dm->device)->mdev;
+	u64 start_addr = mdm->dev_addr + attr->offset;
+	int mode;
 
-	if (attr->access_flags & ~MLX5_IB_DM_ALLOWED_ACCESS)
-		return ERR_PTR(-EINVAL);
+	switch (mdm->type) {
+	case MLX5_IB_UAPI_DM_TYPE_MEMIC:
+		if (attr->access_flags & ~MLX5_IB_DM_MEMIC_ALLOWED_ACCESS)
+			return ERR_PTR(-EINVAL);
 
-	memic_addr = mdm->dev_addr + attr->offset;
+		mode = MLX5_MKC_ACCESS_MODE_MEMIC;
+		start_addr -= pci_resource_start(dev->pdev, 0);
+		break;
+	default:
+		return ERR_PTR(-EINVAL);
+	}
 
-	return mlx5_ib_get_memic_mr(pd, memic_addr, attr->length,
-				    attr->access_flags);
+	return mlx5_ib_get_dm_mr(pd, start_addr, attr->length,
+				 attr->access_flags, mode);
 }
 
 struct ib_mr *mlx5_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
diff --git a/include/uapi/rdma/mlx5_user_ioctl_cmds.h b/include/uapi/rdma/mlx5_user_ioctl_cmds.h
index 0d8f564ce60b..d404c951954c 100644
--- a/include/uapi/rdma/mlx5_user_ioctl_cmds.h
+++ b/include/uapi/rdma/mlx5_user_ioctl_cmds.h
@@ -44,6 +44,7 @@ enum mlx5_ib_create_flow_action_attrs {
 enum mlx5_ib_alloc_dm_attrs {
 	MLX5_IB_ATTR_ALLOC_DM_RESP_START_OFFSET = (1U << UVERBS_ID_NS_SHIFT),
 	MLX5_IB_ATTR_ALLOC_DM_RESP_PAGE_INDEX,
+	MLX5_IB_ATTR_ALLOC_DM_REQ_TYPE,
 };
 
 enum mlx5_ib_devx_methods {
diff --git a/include/uapi/rdma/mlx5_user_ioctl_verbs.h b/include/uapi/rdma/mlx5_user_ioctl_verbs.h
index 0a126a6b9337..c291fb2f8446 100644
--- a/include/uapi/rdma/mlx5_user_ioctl_verbs.h
+++ b/include/uapi/rdma/mlx5_user_ioctl_verbs.h
@@ -57,5 +57,9 @@ struct mlx5_ib_uapi_devx_async_cmd_hdr {
 	__u8		out_data[];
 };
 
+enum mlx5_ib_uapi_dm_type {
+	MLX5_IB_UAPI_DM_TYPE_MEMIC,
+};
+
 #endif
 
-- 
cgit v1.2.3-59-g8ed1b


From 25c13324d03d004f9e8071bf5bf5d5c6fdace71e Mon Sep 17 00:00:00 2001
From: Ariel Levkovich <lariel@mellanox.com>
Date: Sun, 5 May 2019 17:07:13 +0300
Subject: IB/mlx5: Add steering SW ICM device memory type

This patch adds support for allocating, deallocating and registering a new
device memory type, STEERING_SW_ICM.  This memory can be allocated and
used by a privileged user for direct rule insertion and management of the
device's steering tables.

The type is provided by the user via the dedicated attribute in the
alloc_dm ioctl command.

Signed-off-by: Ariel Levkovich <lariel@mellanox.com>
Reviewed-by: Eli Cohen <eli@mellanox.com>
Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
---
 drivers/infiniband/hw/mlx5/cmd.c          | 127 +++++++++++++++++++++++++-
 drivers/infiniband/hw/mlx5/cmd.h          |   6 +-
 drivers/infiniband/hw/mlx5/main.c         | 142 ++++++++++++++++++++++++++++--
 drivers/infiniband/hw/mlx5/mlx5_ib.h      |  17 ++++
 drivers/infiniband/hw/mlx5/mr.c           |   7 ++
 include/uapi/rdma/mlx5_user_ioctl_verbs.h |   2 +
 6 files changed, 292 insertions(+), 9 deletions(-)

(limited to 'include/uapi')

diff --git a/drivers/infiniband/hw/mlx5/cmd.c b/drivers/infiniband/hw/mlx5/cmd.c
index f0e9c7609083..e3ec79b8f7f5 100644
--- a/drivers/infiniband/hw/mlx5/cmd.c
+++ b/drivers/infiniband/hw/mlx5/cmd.c
@@ -157,7 +157,7 @@ int mlx5_cmd_alloc_memic(struct mlx5_dm *dm, phys_addr_t *addr,
 	return -ENOMEM;
 }
 
-int mlx5_cmd_dealloc_memic(struct mlx5_dm *dm, u64 addr, u64 length)
+int mlx5_cmd_dealloc_memic(struct mlx5_dm *dm, phys_addr_t addr, u64 length)
 {
 	struct mlx5_core_dev *dev = dm->dev;
 	u64 hw_start_addr = MLX5_CAP64_DEV_MEM(dev, memic_bar_start_addr);
@@ -186,6 +186,131 @@ int mlx5_cmd_dealloc_memic(struct mlx5_dm *dm, u64 addr, u64 length)
 	return err;
 }
 
+int mlx5_cmd_alloc_sw_icm(struct mlx5_dm *dm, int type, u64 length,
+			  u16 uid, phys_addr_t *addr, u32 *obj_id)
+{
+	struct mlx5_core_dev *dev = dm->dev;
+	u32 num_blocks = DIV_ROUND_UP(length, MLX5_SW_ICM_BLOCK_SIZE(dev));
+	u32 out[MLX5_ST_SZ_DW(general_obj_out_cmd_hdr)] = {};
+	u32 in[MLX5_ST_SZ_DW(create_sw_icm_in)] = {};
+	unsigned long *block_map;
+	u64 icm_start_addr;
+	u32 log_icm_size;
+	u32 max_blocks;
+	u64 block_idx;
+	void *sw_icm;
+	int ret;
+
+	MLX5_SET(general_obj_in_cmd_hdr, in, opcode,
+		 MLX5_CMD_OP_CREATE_GENERAL_OBJECT);
+	MLX5_SET(general_obj_in_cmd_hdr, in, obj_type, MLX5_OBJ_TYPE_SW_ICM);
+	MLX5_SET(general_obj_in_cmd_hdr, in, uid, uid);
+
+	switch (type) {
+	case MLX5_IB_UAPI_DM_TYPE_STEERING_SW_ICM:
+		icm_start_addr = MLX5_CAP64_DEV_MEM(dev,
+						steering_sw_icm_start_address);
+		log_icm_size = MLX5_CAP_DEV_MEM(dev, log_steering_sw_icm_size);
+		block_map = dm->steering_sw_icm_alloc_blocks;
+		break;
+	case MLX5_IB_UAPI_DM_TYPE_HEADER_MODIFY_SW_ICM:
+		icm_start_addr = MLX5_CAP64_DEV_MEM(dev,
+					header_modify_sw_icm_start_address);
+		log_icm_size = MLX5_CAP_DEV_MEM(dev,
+						log_header_modify_sw_icm_size);
+		block_map = dm->header_modify_sw_icm_alloc_blocks;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	max_blocks = BIT(log_icm_size - MLX5_LOG_SW_ICM_BLOCK_SIZE(dev));
+	spin_lock(&dm->lock);
+	block_idx = bitmap_find_next_zero_area(block_map,
+					       max_blocks,
+					       0,
+					       num_blocks, 0);
+
+	if (block_idx < max_blocks)
+		bitmap_set(block_map,
+			   block_idx, num_blocks);
+
+	spin_unlock(&dm->lock);
+
+	if (block_idx >= max_blocks)
+		return -ENOMEM;
+
+	sw_icm = MLX5_ADDR_OF(create_sw_icm_in, in, sw_icm);
+	icm_start_addr += block_idx << MLX5_LOG_SW_ICM_BLOCK_SIZE(dev);
+	MLX5_SET64(sw_icm, sw_icm, sw_icm_start_addr,
+		   icm_start_addr);
+	MLX5_SET(sw_icm, sw_icm, log_sw_icm_size, ilog2(length));
+
+	ret = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+	if (ret) {
+		spin_lock(&dm->lock);
+		bitmap_clear(block_map,
+			     block_idx, num_blocks);
+		spin_unlock(&dm->lock);
+
+		return ret;
+	}
+
+	*addr = icm_start_addr;
+	*obj_id = MLX5_GET(general_obj_out_cmd_hdr, out, obj_id);
+
+	return 0;
+}
+
+int mlx5_cmd_dealloc_sw_icm(struct mlx5_dm *dm, int type, u64 length,
+			    u16 uid, phys_addr_t addr, u32 obj_id)
+{
+	struct mlx5_core_dev *dev = dm->dev;
+	u32 num_blocks = DIV_ROUND_UP(length, MLX5_SW_ICM_BLOCK_SIZE(dev));
+	u32 out[MLX5_ST_SZ_DW(general_obj_out_cmd_hdr)] = {};
+	u32 in[MLX5_ST_SZ_DW(general_obj_in_cmd_hdr)] = {};
+	unsigned long *block_map;
+	u64 start_idx;
+	int err;
+
+	switch (type) {
+	case MLX5_IB_UAPI_DM_TYPE_STEERING_SW_ICM:
+		start_idx =
+			(addr - MLX5_CAP64_DEV_MEM(
+					dev, steering_sw_icm_start_address)) >>
+			MLX5_LOG_SW_ICM_BLOCK_SIZE(dev);
+		block_map = dm->steering_sw_icm_alloc_blocks;
+		break;
+	case MLX5_IB_UAPI_DM_TYPE_HEADER_MODIFY_SW_ICM:
+		start_idx =
+			(addr -
+			 MLX5_CAP64_DEV_MEM(
+				 dev, header_modify_sw_icm_start_address)) >>
+			MLX5_LOG_SW_ICM_BLOCK_SIZE(dev);
+		block_map = dm->header_modify_sw_icm_alloc_blocks;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	MLX5_SET(general_obj_in_cmd_hdr, in, opcode,
+		 MLX5_CMD_OP_DESTROY_GENERAL_OBJECT);
+	MLX5_SET(general_obj_in_cmd_hdr, in, obj_type, MLX5_OBJ_TYPE_SW_ICM);
+	MLX5_SET(general_obj_in_cmd_hdr, in, obj_id, obj_id);
+	MLX5_SET(general_obj_in_cmd_hdr, in, uid, uid);
+
+	err =  mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+	if (err)
+		return err;
+
+	spin_lock(&dm->lock);
+	bitmap_clear(block_map,
+		     start_idx, num_blocks);
+	spin_unlock(&dm->lock);
+
+	return 0;
+}
+
 int mlx5_cmd_query_ext_ppcnt_counters(struct mlx5_core_dev *dev, void *out)
 {
 	u32 in[MLX5_ST_SZ_DW(ppcnt_reg)] = {};
diff --git a/drivers/infiniband/hw/mlx5/cmd.h b/drivers/infiniband/hw/mlx5/cmd.h
index 80a644bea6c7..0572dcba6eae 100644
--- a/drivers/infiniband/hw/mlx5/cmd.h
+++ b/drivers/infiniband/hw/mlx5/cmd.h
@@ -46,7 +46,7 @@ int mlx5_cmd_modify_cong_params(struct mlx5_core_dev *mdev,
 				void *in, int in_size);
 int mlx5_cmd_alloc_memic(struct mlx5_dm *dm, phys_addr_t *addr,
 			 u64 length, u32 alignment);
-int mlx5_cmd_dealloc_memic(struct mlx5_dm *dm, u64 addr, u64 length);
+int mlx5_cmd_dealloc_memic(struct mlx5_dm *dm, phys_addr_t addr, u64 length);
 void mlx5_cmd_dealloc_pd(struct mlx5_core_dev *dev, u32 pdn, u16 uid);
 void mlx5_cmd_destroy_tir(struct mlx5_core_dev *dev, u32 tirn, u16 uid);
 void mlx5_cmd_destroy_tis(struct mlx5_core_dev *dev, u32 tisn, u16 uid);
@@ -65,4 +65,8 @@ int mlx5_cmd_alloc_q_counter(struct mlx5_core_dev *dev, u16 *counter_id,
 			     u16 uid);
 int mlx5_cmd_mad_ifc(struct mlx5_core_dev *dev, const void *inb, void *outb,
 		     u16 opmod, u8 port);
+int mlx5_cmd_alloc_sw_icm(struct mlx5_dm *dm, int type, u64 length,
+			  u16 uid, phys_addr_t *addr, u32 *obj_id);
+int mlx5_cmd_dealloc_sw_icm(struct mlx5_dm *dm, int type, u64 length,
+			    u16 uid, phys_addr_t addr, u32 obj_id);
 #endif /* MLX5_IB_CMD_H */
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 803aea335953..f9def2dfdba3 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -2264,6 +2264,28 @@ static int mlx5_ib_mmap(struct ib_ucontext *ibcontext, struct vm_area_struct *vm
 	return 0;
 }
 
+static inline int check_dm_type_support(struct mlx5_ib_dev *dev,
+					u32 type)
+{
+	switch (type) {
+	case MLX5_IB_UAPI_DM_TYPE_MEMIC:
+		if (!MLX5_CAP_DEV_MEM(dev->mdev, memic))
+			return -EOPNOTSUPP;
+		break;
+	case MLX5_IB_UAPI_DM_TYPE_STEERING_SW_ICM:
+		if (!capable(CAP_SYS_RAWIO) ||
+		    !capable(CAP_NET_RAW))
+			return -EPERM;
+
+		if (!(MLX5_CAP_FLOWTABLE_NIC_RX(dev->mdev, sw_owner) ||
+		      MLX5_CAP_FLOWTABLE_NIC_TX(dev->mdev, sw_owner)))
+			return -EOPNOTSUPP;
+		break;
+	}
+
+	return 0;
+}
+
 static int handle_alloc_dm_memic(struct ib_ucontext *ctx,
 				 struct mlx5_ib_dm *dm,
 				 struct ib_dm_alloc_attr *attr,
@@ -2309,6 +2331,40 @@ err_dealloc:
 	return err;
 }
 
+static int handle_alloc_dm_sw_icm(struct ib_ucontext *ctx,
+				  struct mlx5_ib_dm *dm,
+				  struct ib_dm_alloc_attr *attr,
+				  struct uverbs_attr_bundle *attrs,
+				  int type)
+{
+	struct mlx5_dm *dm_db = &to_mdev(ctx->device)->dm;
+	u64 act_size;
+	int err;
+
+	/* Allocation size must a multiple of the basic block size
+	 * and a power of 2.
+	 */
+	act_size = roundup(attr->length, MLX5_SW_ICM_BLOCK_SIZE(dm_db->dev));
+	act_size = roundup_pow_of_two(act_size);
+
+	dm->size = act_size;
+	err = mlx5_cmd_alloc_sw_icm(dm_db, type, act_size,
+				    to_mucontext(ctx)->devx_uid, &dm->dev_addr,
+				    &dm->icm_dm.obj_id);
+	if (err)
+		return err;
+
+	err = uverbs_copy_to(attrs,
+			     MLX5_IB_ATTR_ALLOC_DM_RESP_START_OFFSET,
+			     &dm->dev_addr, sizeof(dm->dev_addr));
+	if (err)
+		mlx5_cmd_dealloc_sw_icm(dm_db, type, dm->size,
+					to_mucontext(ctx)->devx_uid,
+					dm->dev_addr, dm->icm_dm.obj_id);
+
+	return err;
+}
+
 struct ib_dm *mlx5_ib_alloc_dm(struct ib_device *ibdev,
 			       struct ib_ucontext *context,
 			       struct ib_dm_alloc_attr *attr,
@@ -2327,6 +2383,10 @@ struct ib_dm *mlx5_ib_alloc_dm(struct ib_device *ibdev,
 	mlx5_ib_dbg(to_mdev(ibdev), "alloc_dm req: dm_type=%d user_length=0x%llx log_alignment=%d\n",
 		    type, attr->length, attr->alignment);
 
+	err = check_dm_type_support(to_mdev(ibdev), type);
+	if (err)
+		return ERR_PTR(err);
+
 	dm = kzalloc(sizeof(*dm), GFP_KERNEL);
 	if (!dm)
 		return ERR_PTR(-ENOMEM);
@@ -2339,6 +2399,10 @@ struct ib_dm *mlx5_ib_alloc_dm(struct ib_device *ibdev,
 					    attr,
 					    attrs);
 		break;
+	case MLX5_IB_UAPI_DM_TYPE_STEERING_SW_ICM:
+	case MLX5_IB_UAPI_DM_TYPE_HEADER_MODIFY_SW_ICM:
+		err = handle_alloc_dm_sw_icm(context, dm, attr, attrs, type);
+		break;
 	default:
 		err = -EOPNOTSUPP;
 	}
@@ -2355,6 +2419,8 @@ err_free:
 
 int mlx5_ib_dealloc_dm(struct ib_dm *ibdm, struct uverbs_attr_bundle *attrs)
 {
+	struct mlx5_ib_ucontext *ctx = rdma_udata_to_drv_context(
+		&attrs->driver_udata, struct mlx5_ib_ucontext, ibucontext);
 	struct mlx5_dm *dm_db = &to_mdev(ibdm->device)->dm;
 	struct mlx5_ib_dm *dm = to_mdm(ibdm);
 	u32 page_idx;
@@ -2371,11 +2437,16 @@ int mlx5_ib_dealloc_dm(struct ib_dm *ibdm, struct uverbs_attr_bundle *attrs)
 			    MLX5_CAP64_DEV_MEM(dm_db->dev,
 					       memic_bar_start_addr)) >>
 			   PAGE_SHIFT;
-		bitmap_clear(rdma_udata_to_drv_context(&attrs->driver_udata,
-						       struct mlx5_ib_ucontext,
-						       ibucontext)
-				     ->dm_pages,
-			     page_idx, DIV_ROUND_UP(dm->size, PAGE_SIZE));
+		bitmap_clear(ctx->dm_pages, page_idx,
+			     DIV_ROUND_UP(dm->size, PAGE_SIZE));
+		break;
+	case MLX5_IB_UAPI_DM_TYPE_STEERING_SW_ICM:
+	case MLX5_IB_UAPI_DM_TYPE_HEADER_MODIFY_SW_ICM:
+		ret = mlx5_cmd_dealloc_sw_icm(dm_db, dm->type, dm->size,
+					      ctx->devx_uid, dm->dev_addr,
+					      dm->icm_dm.obj_id);
+		if (ret)
+			return ret;
 		break;
 	default:
 		return -EOPNOTSUPP;
@@ -5902,6 +5973,8 @@ static struct ib_counters *mlx5_ib_create_counters(struct ib_device *device,
 
 static void mlx5_ib_stage_init_cleanup(struct mlx5_ib_dev *dev)
 {
+	struct mlx5_core_dev *mdev = dev->mdev;
+
 	mlx5_ib_cleanup_multiport_master(dev);
 	if (IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING)) {
 		srcu_barrier(&dev->mr_srcu);
@@ -5909,11 +5982,29 @@ static void mlx5_ib_stage_init_cleanup(struct mlx5_ib_dev *dev)
 	}
 
 	WARN_ON(!bitmap_empty(dev->dm.memic_alloc_pages, MLX5_MAX_MEMIC_PAGES));
+
+	WARN_ON(dev->dm.steering_sw_icm_alloc_blocks &&
+		!bitmap_empty(
+			dev->dm.steering_sw_icm_alloc_blocks,
+			BIT(MLX5_CAP_DEV_MEM(mdev, log_steering_sw_icm_size) -
+			    MLX5_LOG_SW_ICM_BLOCK_SIZE(mdev))));
+
+	kfree(dev->dm.steering_sw_icm_alloc_blocks);
+
+	WARN_ON(dev->dm.header_modify_sw_icm_alloc_blocks &&
+		!bitmap_empty(dev->dm.header_modify_sw_icm_alloc_blocks,
+			      BIT(MLX5_CAP_DEV_MEM(
+					  mdev, log_header_modify_sw_icm_size) -
+				  MLX5_LOG_SW_ICM_BLOCK_SIZE(mdev))));
+
+	kfree(dev->dm.header_modify_sw_icm_alloc_blocks);
 }
 
 static int mlx5_ib_stage_init_init(struct mlx5_ib_dev *dev)
 {
 	struct mlx5_core_dev *mdev = dev->mdev;
+	u64 header_modify_icm_blocks = 0;
+	u64 steering_icm_blocks = 0;
 	int err;
 	int i;
 
@@ -5959,16 +6050,51 @@ static int mlx5_ib_stage_init_init(struct mlx5_ib_dev *dev)
 	INIT_LIST_HEAD(&dev->qp_list);
 	spin_lock_init(&dev->reset_flow_resource_lock);
 
+	if (MLX5_CAP_GEN_64(mdev, general_obj_types) &
+	    MLX5_GENERAL_OBJ_TYPES_CAP_SW_ICM) {
+		if (MLX5_CAP64_DEV_MEM(mdev, steering_sw_icm_start_address)) {
+			steering_icm_blocks =
+				BIT(MLX5_CAP_DEV_MEM(mdev,
+						     log_steering_sw_icm_size) -
+				    MLX5_LOG_SW_ICM_BLOCK_SIZE(mdev));
+
+			dev->dm.steering_sw_icm_alloc_blocks =
+				kcalloc(BITS_TO_LONGS(steering_icm_blocks),
+					sizeof(unsigned long), GFP_KERNEL);
+			if (!dev->dm.steering_sw_icm_alloc_blocks)
+				goto err_mp;
+		}
+
+		if (MLX5_CAP64_DEV_MEM(mdev,
+				       header_modify_sw_icm_start_address)) {
+			header_modify_icm_blocks = BIT(
+				MLX5_CAP_DEV_MEM(
+					mdev, log_header_modify_sw_icm_size) -
+				MLX5_LOG_SW_ICM_BLOCK_SIZE(mdev));
+
+			dev->dm.header_modify_sw_icm_alloc_blocks =
+				kcalloc(BITS_TO_LONGS(header_modify_icm_blocks),
+					sizeof(unsigned long), GFP_KERNEL);
+			if (!dev->dm.header_modify_sw_icm_alloc_blocks)
+				goto err_dm;
+		}
+	}
+
 	spin_lock_init(&dev->dm.lock);
 	dev->dm.dev = mdev;
 
 	if (IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING)) {
 		err = init_srcu_struct(&dev->mr_srcu);
 		if (err)
-			goto err_mp;
+			goto err_dm;
 	}
 
 	return 0;
+
+err_dm:
+	kfree(dev->dm.steering_sw_icm_alloc_blocks);
+	kfree(dev->dm.header_modify_sw_icm_alloc_blocks);
+
 err_mp:
 	mlx5_ib_cleanup_multiport_master(dev);
 
@@ -6151,7 +6277,9 @@ static int mlx5_ib_stage_caps_init(struct mlx5_ib_dev *dev)
 		ib_set_device_ops(&dev->ib_dev, &mlx5_ib_dev_xrc_ops);
 	}
 
-	if (MLX5_CAP_DEV_MEM(mdev, memic))
+	if (MLX5_CAP_DEV_MEM(mdev, memic) ||
+	    MLX5_CAP_GEN_64(dev->mdev, general_obj_types) &
+	    MLX5_GENERAL_OBJ_TYPES_CAP_SW_ICM)
 		ib_set_device_ops(&dev->ib_dev, &mlx5_ib_dev_dm_ops);
 
 	if (mlx5_accel_ipsec_device_caps(dev->mdev) &
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index 714c360dc9fb..40eb8be482e4 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -118,6 +118,10 @@ enum {
 	MLX5_MEMIC_BASE_SIZE	= 1 << MLX5_MEMIC_BASE_ALIGN,
 };
 
+#define MLX5_LOG_SW_ICM_BLOCK_SIZE(dev)                                        \
+	(MLX5_CAP_DEV_MEM(dev, log_sw_icm_alloc_granularity))
+#define MLX5_SW_ICM_BLOCK_SIZE(dev) (1 << MLX5_LOG_SW_ICM_BLOCK_SIZE(dev))
+
 struct mlx5_ib_ucontext {
 	struct ib_ucontext	ibucontext;
 	struct list_head	db_page_list;
@@ -557,6 +561,12 @@ struct mlx5_ib_dm {
 	phys_addr_t		dev_addr;
 	u32			type;
 	size_t			size;
+	union {
+		struct {
+			u32	obj_id;
+		} icm_dm;
+		/* other dm types specific params should be added here */
+	};
 };
 
 #define MLX5_IB_MTT_PRESENT (MLX5_IB_MTT_READ | MLX5_IB_MTT_WRITE)
@@ -567,6 +577,11 @@ struct mlx5_ib_dm {
 					 IB_ACCESS_REMOTE_ATOMIC |\
 					 IB_ZERO_BASED)
 
+#define MLX5_IB_DM_SW_ICM_ALLOWED_ACCESS (IB_ACCESS_LOCAL_WRITE   |\
+					  IB_ACCESS_REMOTE_WRITE  |\
+					  IB_ACCESS_REMOTE_READ   |\
+					  IB_ZERO_BASED)
+
 struct mlx5_ib_mr {
 	struct ib_mr		ibmr;
 	void			*descs;
@@ -854,6 +869,8 @@ struct mlx5_dm {
 	 */
 	spinlock_t lock;
 	DECLARE_BITMAP(memic_alloc_pages, MLX5_MAX_MEMIC_PAGES);
+	unsigned long *steering_sw_icm_alloc_blocks;
+	unsigned long *header_modify_sw_icm_alloc_blocks;
 };
 
 struct mlx5_read_counters_attr {
diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index ba35d68e7499..5f09699fab98 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -1247,6 +1247,13 @@ struct ib_mr *mlx5_ib_reg_dm_mr(struct ib_pd *pd, struct ib_dm *dm,
 		mode = MLX5_MKC_ACCESS_MODE_MEMIC;
 		start_addr -= pci_resource_start(dev->pdev, 0);
 		break;
+	case MLX5_IB_UAPI_DM_TYPE_STEERING_SW_ICM:
+	case MLX5_IB_UAPI_DM_TYPE_HEADER_MODIFY_SW_ICM:
+		if (attr->access_flags & ~MLX5_IB_DM_SW_ICM_ALLOWED_ACCESS)
+			return ERR_PTR(-EINVAL);
+
+		mode = MLX5_MKC_ACCESS_MODE_SW_ICM;
+		break;
 	default:
 		return ERR_PTR(-EINVAL);
 	}
diff --git a/include/uapi/rdma/mlx5_user_ioctl_verbs.h b/include/uapi/rdma/mlx5_user_ioctl_verbs.h
index c291fb2f8446..a8f34c237458 100644
--- a/include/uapi/rdma/mlx5_user_ioctl_verbs.h
+++ b/include/uapi/rdma/mlx5_user_ioctl_verbs.h
@@ -59,6 +59,8 @@ struct mlx5_ib_uapi_devx_async_cmd_hdr {
 
 enum mlx5_ib_uapi_dm_type {
 	MLX5_IB_UAPI_DM_TYPE_MEMIC,
+	MLX5_IB_UAPI_DM_TYPE_STEERING_SW_ICM,
+	MLX5_IB_UAPI_DM_TYPE_HEADER_MODIFY_SW_ICM,
 };
 
 #endif
-- 
cgit v1.2.3-59-g8ed1b


From f95be3d28d891b0c0f339a504e3aa8e382bbd9a6 Mon Sep 17 00:00:00 2001
From: Gal Pressman <galpress@amazon.com>
Date: Sun, 5 May 2019 20:59:21 +0300
Subject: RDMA: Add EFA related definitions

Add EFA driver ID to the IOCTL interface uapi. This patch also adds
unspecified node/transport type that will be used by EFA (usnic is left
unchanged as it's already part of our ABI).

Signed-off-by: Gal Pressman <galpress@amazon.com>
Reviewed-by: Shiraz Saleem <shiraz.saleem@intel.com>
Reviewed-by: Steve Wise <swise@opengridcomputing.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
---
 drivers/infiniband/core/sysfs.c          | 1 +
 drivers/infiniband/core/verbs.c          | 2 ++
 include/rdma/ib_verbs.h                  | 4 +++-
 include/uapi/rdma/rdma_user_ioctl_cmds.h | 1 +
 4 files changed, 7 insertions(+), 1 deletion(-)

(limited to 'include/uapi')

diff --git a/drivers/infiniband/core/sysfs.c b/drivers/infiniband/core/sysfs.c
index 8c7adc27aeea..c78d0c9646ae 100644
--- a/drivers/infiniband/core/sysfs.c
+++ b/drivers/infiniband/core/sysfs.c
@@ -1201,6 +1201,7 @@ static ssize_t node_type_show(struct device *device,
 	case RDMA_NODE_RNIC:	  return sprintf(buf, "%d: RNIC\n", dev->node_type);
 	case RDMA_NODE_USNIC:	  return sprintf(buf, "%d: usNIC\n", dev->node_type);
 	case RDMA_NODE_USNIC_UDP: return sprintf(buf, "%d: usNIC UDP\n", dev->node_type);
+	case RDMA_NODE_UNSPECIFIED: return sprintf(buf, "%d: unspecified\n", dev->node_type);
 	case RDMA_NODE_IB_SWITCH: return sprintf(buf, "%d: switch\n", dev->node_type);
 	case RDMA_NODE_IB_ROUTER: return sprintf(buf, "%d: router\n", dev->node_type);
 	default:		  return sprintf(buf, "%d: <unknown>\n", dev->node_type);
diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index a4e97dd3c4b6..e666a1f7608d 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -218,6 +218,8 @@ rdma_node_get_transport(enum rdma_node_type node_type)
 		return RDMA_TRANSPORT_USNIC_UDP;
 	if (node_type == RDMA_NODE_RNIC)
 		return RDMA_TRANSPORT_IWARP;
+	if (node_type == RDMA_NODE_UNSPECIFIED)
+		return RDMA_TRANSPORT_UNSPECIFIED;
 
 	return RDMA_TRANSPORT_IB;
 }
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index deb67b21ccb9..0742095355f2 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -140,6 +140,7 @@ enum rdma_node_type {
 	RDMA_NODE_RNIC,
 	RDMA_NODE_USNIC,
 	RDMA_NODE_USNIC_UDP,
+	RDMA_NODE_UNSPECIFIED,
 };
 
 enum {
@@ -151,7 +152,8 @@ enum rdma_transport_type {
 	RDMA_TRANSPORT_IB,
 	RDMA_TRANSPORT_IWARP,
 	RDMA_TRANSPORT_USNIC,
-	RDMA_TRANSPORT_USNIC_UDP
+	RDMA_TRANSPORT_USNIC_UDP,
+	RDMA_TRANSPORT_UNSPECIFIED,
 };
 
 enum rdma_protocol_type {
diff --git a/include/uapi/rdma/rdma_user_ioctl_cmds.h b/include/uapi/rdma/rdma_user_ioctl_cmds.h
index 06c34d99be85..26213f49f5c8 100644
--- a/include/uapi/rdma/rdma_user_ioctl_cmds.h
+++ b/include/uapi/rdma/rdma_user_ioctl_cmds.h
@@ -102,6 +102,7 @@ enum rdma_driver_id {
 	RDMA_DRIVER_RXE,
 	RDMA_DRIVER_HFI1,
 	RDMA_DRIVER_QIB,
+	RDMA_DRIVER_EFA,
 };
 
 #endif
-- 
cgit v1.2.3-59-g8ed1b


From 2ce62149afaece4baee21ad2b925ae1d089b4e3b Mon Sep 17 00:00:00 2001
From: Gal Pressman <galpress@amazon.com>
Date: Sun, 5 May 2019 20:59:26 +0300
Subject: RDMA/efa: Add the ABI definitions

Add the EFA ABI file exposed to userspace.

Signed-off-by: Gal Pressman <galpress@amazon.com>
Reviewed-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
---
 include/uapi/rdma/efa-abi.h | 101 ++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 101 insertions(+)
 create mode 100644 include/uapi/rdma/efa-abi.h

(limited to 'include/uapi')

diff --git a/include/uapi/rdma/efa-abi.h b/include/uapi/rdma/efa-abi.h
new file mode 100644
index 000000000000..9599a2a62be8
--- /dev/null
+++ b/include/uapi/rdma/efa-abi.h
@@ -0,0 +1,101 @@
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */
+/*
+ * Copyright 2018-2019 Amazon.com, Inc. or its affiliates. All rights reserved.
+ */
+
+#ifndef EFA_ABI_USER_H
+#define EFA_ABI_USER_H
+
+#include <linux/types.h>
+
+/*
+ * Increment this value if any changes that break userspace ABI
+ * compatibility are made.
+ */
+#define EFA_UVERBS_ABI_VERSION 1
+
+/*
+ * Keep structs aligned to 8 bytes.
+ * Keep reserved fields as arrays of __u8 named reserved_XXX where XXX is the
+ * hex bit offset of the field.
+ */
+
+enum efa_ibv_user_cmds_supp_udata {
+	EFA_USER_CMDS_SUPP_UDATA_QUERY_DEVICE = 1 << 0,
+	EFA_USER_CMDS_SUPP_UDATA_CREATE_AH    = 1 << 1,
+};
+
+struct efa_ibv_alloc_ucontext_resp {
+	__u32 comp_mask;
+	__u32 cmds_supp_udata_mask;
+	__u16 sub_cqs_per_cq;
+	__u16 inline_buf_size;
+	__u32 max_llq_size; /* bytes */
+};
+
+struct efa_ibv_alloc_pd_resp {
+	__u32 comp_mask;
+	__u16 pdn;
+	__u8 reserved_30[2];
+};
+
+struct efa_ibv_create_cq {
+	__u32 comp_mask;
+	__u32 cq_entry_size;
+	__u16 num_sub_cqs;
+	__u8 reserved_50[6];
+};
+
+struct efa_ibv_create_cq_resp {
+	__u32 comp_mask;
+	__u8 reserved_20[4];
+	__aligned_u64 q_mmap_key;
+	__aligned_u64 q_mmap_size;
+	__u16 cq_idx;
+	__u8 reserved_d0[6];
+};
+
+enum {
+	EFA_QP_DRIVER_TYPE_SRD = 0,
+};
+
+struct efa_ibv_create_qp {
+	__u32 comp_mask;
+	__u32 rq_ring_size; /* bytes */
+	__u32 sq_ring_size; /* bytes */
+	__u32 driver_qp_type;
+};
+
+struct efa_ibv_create_qp_resp {
+	__u32 comp_mask;
+	/* the offset inside the page of the rq db */
+	__u32 rq_db_offset;
+	/* the offset inside the page of the sq db */
+	__u32 sq_db_offset;
+	/* the offset inside the page of descriptors buffer */
+	__u32 llq_desc_offset;
+	__aligned_u64 rq_mmap_key;
+	__aligned_u64 rq_mmap_size;
+	__aligned_u64 rq_db_mmap_key;
+	__aligned_u64 sq_db_mmap_key;
+	__aligned_u64 llq_desc_mmap_key;
+	__u16 send_sub_cq_idx;
+	__u16 recv_sub_cq_idx;
+	__u8 reserved_1e0[4];
+};
+
+struct efa_ibv_create_ah_resp {
+	__u32 comp_mask;
+	__u16 efa_address_handle;
+	__u8 reserved_30[2];
+};
+
+struct efa_ibv_ex_query_device_resp {
+	__u32 comp_mask;
+	__u32 max_sq_wr;
+	__u32 max_rq_wr;
+	__u16 max_sq_sge;
+	__u16 max_rq_sge;
+};
+
+#endif /* EFA_ABI_USER_H */
-- 
cgit v1.2.3-59-g8ed1b